Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 139 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1613. Min Range: -0.1613

Max Act: 0.1613. Min Act: -0.0001

Data Index: 217107 (C4 (Web Text))

Max Activating Token Index: 844

Text #1

Max Range: 0.1613. Min Range: -0.1613

Max Act: 0.1368. Min Act: -0.0001

Data Index: 977031 (C4 (Web Text))

Max Activating Token Index: 335

Text #2

Max Range: 0.1613. Min Range: -0.1613

Max Act: 0.1342. Min Act: -0.0001

Data Index: 894364 (C4 (Web Text))

Max Activating Token Index: 919

Text #3

Max Range: 0.1613. Min Range: -0.1613

Max Act: 0.1441. Min Act: -0.0001

Data Index: 1239292 (C4 (Web Text))

Max Activating Token Index: 834

Text #4

Max Range: 0.1613. Min Range: -0.1613

Max Act: 0.1308. Min Act: -0.0001

Data Index: 349257 (C4 (Web Text))

Max Activating Token Index: 911

Text #5

Max Range: 0.1613. Min Range: -0.1613

Max Act: 0.1211. Min Act: -0.0001

Data Index: 1221839 (C4 (Web Text))

Max Activating Token Index: 746

Text #6

Max Range: 0.1613. Min Range: -0.1613

Max Act: 0.1372. Min Act: -0.0001

Data Index: 334247 (C4 (Web Text))

Max Activating Token Index: 823

Text #7

Max Range: 0.1613. Min Range: -0.1613

Max Act: 0.1290. Min Act: -0.0001

Data Index: 1291272 (C4 (Web Text))

Max Activating Token Index: 346

Text #8

Max Range: 0.1613. Min Range: -0.1613

Max Act: 0.1252. Min Act: -0.0001

Data Index: 1069923 (C4 (Web Text))

Max Activating Token Index: 1017

Text #9

Max Range: 0.1613. Min Range: -0.1613

Max Act: 0.1229. Min Act: -0.0001

Data Index: 251555 (C4 (Web Text))

Max Activating Token Index: 32

Text #10

Max Range: 0.1613. Min Range: -0.1613

Max Act: 0.1309. Min Act: -0.0001

Data Index: 947526 (C4 (Web Text))

Max Activating Token Index: 6

Text #11

Max Range: 0.1613. Min Range: -0.1613

Max Act: 0.1208. Min Act: -0.0001

Data Index: 30076 (C4 (Web Text))

Max Activating Token Index: 69

Text #12

Max Range: 0.1613. Min Range: -0.1613

Max Act: 0.1216. Min Act: -0.0001

Data Index: 583210 (C4 (Web Text))

Max Activating Token Index: 439

Text #13

Max Range: 0.1613. Min Range: -0.1613

Max Act: 0.1229. Min Act: -0.0001

Data Index: 681208 (C4 (Web Text))

Max Activating Token Index: 13

Text #14

Max Range: 0.1613. Min Range: -0.1613

Max Act: 0.1134. Min Act: -0.0001

Data Index: 1220117 (C4 (Web Text))

Max Activating Token Index: 371

Text #15

Max Range: 0.1613. Min Range: -0.1613

Max Act: 0.1236. Min Act: -0.0001

Data Index: 1171711 (C4 (Web Text))

Max Activating Token Index: 966

Text #16

Max Range: 0.1613. Min Range: -0.1613

Max Act: 0.0982. Min Act: -0.0001

Data Index: 388890 (C4 (Web Text))

Max Activating Token Index: 283

Text #17

Max Range: 0.1613. Min Range: -0.1613

Max Act: 0.1149. Min Act: -0.0001

Data Index: 733600 (C4 (Web Text))

Max Activating Token Index: 986

Text #18

Max Range: 0.1613. Min Range: -0.1613

Max Act: 0.1125. Min Act: -0.0001

Data Index: 110886 (C4 (Web Text))

Max Activating Token Index: 108

Text #19

Max Range: 0.1613. Min Range: -0.1613

Max Act: 0.1176. Min Act: -0.0001

Data Index: 841833 (C4 (Web Text))

Max Activating Token Index: 873